cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
mib.stmikbd@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
JURNAL MEDIA INFORMATIKA BUDIDARMA
ISSN : 26145278     EISSN : 25488368     DOI : http://dx.doi.org/10.30865/mib.v3i1.1060
Decission Support System, Expert System, Informatics tecnique, Information System, Cryptography, Networking, Security, Computer Science, Image Processing, Artificial Inteligence, Steganography etc (related to informatics and computer science)
Articles 44 Documents
Search results for , issue "Vol 4, No 4 (2020): Oktober 2020" : 44 Documents clear
Bagian 2: Model Arsitektur Neural Network Dengan Kombinasi K-Medoids dan Backpropagation pada kasus Pandemi Covid-19 di Indonesia Windarto, Agus Perdana; Na`am, Jufriadif; Yuhandri, Yuhandri; Wanto, Anjar; Mesran, Mesran
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v4i4.2505

Abstract

The aim of the research is to create a prediction model on the best neural network architecture by combining the k-medoids and backpropagation methods in the case of the COVID-19 pandemic in Indonesia. Data obtained from the Ministry of Health is sampled and processed from covid19.go.id and bnpb.go.id. The case raised was the number of the spread of the COVID-19 pandemic in Indonesia as of July 7, 2020, with 34 records. The variables used in this study are the number of positive cases (x1), the number of cases cured (x2), and the number of deaths (x3) by province. The process of data analysis uses the help of RapidMiner software. The solution provided is to combine the k-medoids and backpropagation methods. Where the k-medoids method is mapping the specified cluster. The cluster labels used are high cluster (C1 = red zone), alert cluster (C2 = yellow zone), low cluster (C3 = green zone). The results of cluster mapping are continued to the backpropagation method to predict the accuracy of the existing cluster results. By using the best architectural model 3-2-1, the accuracy value is 94.17% with learning_rate = 0.696. Cluster mapping results obtained nine provinces are in the high cluster (C1 = red zone), three provinces are in the alert cluster (C2 = yellow zone), and 22 provinces are in the low cluster (C3 = green zone). It is expected that the results of the research can provide information to the government in the form of cluster mapping of regions in Indonesia.
Implementasi Teorema Bayes Dalam Diagnosa Penyakit Ayam Broiler Nasyuha, Asyahri Hadi; Hafizah, Hafizah
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v4i4.2366

Abstract

Broiler chickens are a type of chicken produced from the cultivation of animal husbandry technology which has a characteristic of fast growth, as a meat producer with low feed conversion and is ready to slaughter at the age of 28-45 days. Chicken health affects the benefits that will be obtained by the farmer, therefore the Expert System for diagnosing chicken disease using the Bayes Theorem method was developed to help users, especially broiler chicken breeders, in diagnosing diseases along with suggestions or recommended countermeasures. The application of the Bayes Theorem method in diagnosing disease in broilers is by entering the calculation algorithm of the Bayes Theorem method into the system, so that the expert system can perform calculations using the Bayes Theorem method and provide diagnostic results and correct solutions to the specified disease.
Klasifikasi Argument Pada Teks dengan Menggunakan Metode Multinomial Logistic Regression Terhadap Kasus Pemindahan Ibu Kota Indonesia di Twitter Rizaldi, Mochammad Naufal; Adiwijaya, Adiwijaya; Faraby, Said Al
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v4i4.2348

Abstract

Information on moving the Indonesian capital from Jakarta to East Kalimantan certainly raises the pros and cons conveyed by the Indonesian people through the Twitter social network. However, the pros and cons comments are of course varied, accompanied or not accompanied by arguments or even completely unrelated to the topic under discussion. User limitations in filtering out that information will certainly make it difficult for the public or even the government to analyze the information contained in the tweet. Therefore, a system was built that could classify tweets automatically into three classes, namely non-arbitration, argument and unknown. The method used in this research is Multinomial Logistic Regression (MLR). MLR is a generalization method of Logistic Regression and is used to classify 3 or more classes. Before the classification process is carried out, the tweet must be preprocessed in order to make the tweet clear of all existing noise. Feature extractions used in this study include unigram, bigram and trigram. In this study, there are 12 test scenarios and comparison methods, namely Artificial Neural Network (ANN). Of all the test scenarios the best results for the MLR method are SRU with an accuracy of 41,30%, while for the ANN method namely the RU scenario with an accuracy of 45,10%.
Sistem Manajemen Absensi dengan Fitur Pengenalan Wajah dan GPS Menggunakan YOLO pada Platform Android Hartiwi, Yessi; Rasywir, Errissya; Pratama, Yovi; Jusia, Pareza Alam
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v4i4.2522

Abstract

This study offers an attendance system that can be run with the Global Positioning System (GPS) feature to automatically check the location of the face owner. Recently, the YOLO algorithm is the world's most popular method of facial recognition. Currently the You Only Look Once (YOLO) algorithm toolbox has been provided in various programming language platforms for use. The system we offer is also able to check the position or whereabouts of objects using Global Positioning System (GPS) technology. The results of this test obtained an accuracy of 0.93435 and the lowest was within the range of 93%, while the average accuracy values were 93.26%. Of the 20 assessment data carried out by the Attendance Management System with Face Recognition and GPS Features using YOLO on the Android Platform. The evaluation of the accuracy of student attendance is expected to support the process of academic activities on campus. In addition, this product is expected to be able to assist management who require evaluation results as well as an effort to improve business processes in an agency in order to improve their performance. This research proves that the use of the tool library with the You Only Look Once (YOLO) algorithm is the most popular method in the world of facial recognition and is proven to be tough and very good at this time.
Penerapan Data Mining Pada Penerimaan Dosen Tetap Menggunakan Metode Naive Bayes Classifier dan C4.5 Sadikin, Muhammad; Rosnelly, Rika; Roslina, Roslina; Gunawan, Teddy Surya; Wanayumini, Wanayumini
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v4i4.2434

Abstract

Recruitment is an important step in creating professional HR (Human Resources). The application of classification methods such as the Naïve Bayes method and C4.5 can be used in the classification of potential lecturers and can be accepted by the campus by calculating the equations for each criterion. The difficulty experienced is the ineffective use of the method to generate the required lecturer acceptance so that it is not in accordance with the applicant's expertise. One of the classification methods applied to data mining is the naïve Bayes method and C4.5. The purpose of this study is to determine the level of accuracy of the two methods used by using the Weka 3.8 tool based on the calculation of Correctly Classified Instance and Incorrectly Classified Instance. The accuracy results obtained with the naïve Bayes method are 83.7838% and the C4.5 method is 91.8919% from 37 training data. So the C4.5 method is a more appropriate method to use than naïve Bayes.
Penentuan Siswa SMK Kimia Analisa Terbaik Yang Akan Dikirim Mengikuti Olimpiade Kimia Tingkat Nasional Menerapkan Metode Entropy dan MOORA Yendrizal, Yendrizal
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v4i4.2350

Abstract

SMK Chemistry Analysis is a special and concentrated junior high school in matters related to chemistry, chemistry is very important in human life because every element on earth contains chemicals so chemistry is a department that is very much in demand by many circles, both industrial and non-industrial, so that many students, especially those majoring in Chemistry Analysis, want to do their best to prove their ability in the lessons they persevere by taking part in the Olympics, the Olympics that are followed are usually at the national level between SMK / SMA students and the equivalent which will later become an honor If you can win the chemistry Olympiad, to win an Olympiad it takes students who are really able to take part in competitions, of course schools need to make a selection first in order to get students who really excel and deserve to take part in the Olympics, in the selection it must be done. Do it systematically in order to produce fairness in student selection and minimize failures in participating in the national level chemistry Olympiad, namely by using a decision support system by applying the MOORA method which previously used the entropy method in obtaining subjective weights that will be used in calculating all aspects of decision support
Penerapan Algoritma K-Means Untuk Pengelompokkan Penyakit Kronis pada Warga Lansia (Studi Kasus Pada: Posyandu Lansia RW 07) Utomo, Wargijono
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v4i4.2410

Abstract

Health is very valuable for all humans, anyone can experience health problems, especially for the elderly. Posyandu elderly RW 07 Pulogebang sub-district is one of the health services available for elderly residents. One of the government's efforts to deal with health problems is by establishing posyandu for elderly residents, considering how elderly people are vulnerable to health problems. At this time, health problems have the potential to attack people who are elderly, and have a history of chronic disease and a weak immune system, more likely to develop disease. In order to provide proper treatment, the elderly posyandu officers classify elderly people who have a history of chronic disease so that they can provide appropriate education and treatment. The data collection and counseling methods carried out by the elderly posyandu are still random and take turns with elderly residents in RW 07, Pulogebang sub-district. However, this method has the risk of being less accurate with the resulting data, because each resident has a different history of disease. Therefore we need an analysis of the health data of the elderly, so that it can be seen the distribution of people who have a history of chronic disease. One solution is to use data mining. So that in this study the clustering technique was used using the K-Means algorithm to classify patients with chronic disease in the elderly residents of RW 07, Pulogebang Village.
Analisis Kepuasan Alumni Terhadap Pelayanan Akademik dengan Metode Importance Performance Analysis Berbasis Web (Studi Kasus: Universitas CIC) Asfi, Marsani; Kusnadi, Kusnadi; Kristianto, Kristianto
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v4i4.2343

Abstract

Increasing development of information technology and competition among tertiary institutions, analysis quality of academic services in the competitive era such as now is an important thing for university to do. The purpose of this research is to build a web-based computer system for analyzing alumni satisfaction with the quality of academic services at CIC University, the sample data used were 31 Alumni CIC University who graduates in 2019. The analytical method used was Importance Performance Analysis method, this method is an analysis technique which is used to find out which attributes have a big influence on satisfaction, where the measured attributes will be grouped in 4 quadrants. The results of this research is alumni satisfaction analysis systems for academic services at CIC University with Importance Performance Analysis method. The results of the system test of 31 alumni sample data assessing 9 attributes of academic services at CIC University, obtained 33.33% or 3 attributes included in Quadrant I which means that attributes are recommended to be improved. 11.11% or 1 attribute included in the Quadrant II, it mean that attribute has succeeded in satisfying the Alumni and its performance must be maintained. 22.22% or 2 attributes are in the Quadrant III category, it mean that atrributes have a low priority to be improved. While in Quadrant IV there are 33.33% or 3 attributes, it mean that these attributes have good performance, but are not considered important by Alumni
Lodging Recommendations Using the SparkML Engine ALS and Surprise SVD Ramadhan, Sageri Fikri; Baizal, Z K Abdurahman; Rismala, Rita
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v%vi%i.2257

Abstract

Recommendation system is a process or tool used to provide predictions for users to choose something based on an existing domain. This system has become a primary need for today's modern digital industry such as in the entertainment, shopping, and service sectors. In this research, we focus on how to develop a recommendation system for accommodation services. We use the Alternating Least Square and Singular Value Decomposition methods to predict and recommend lodging to users
Perancangan Aplikasi Antrean Online Pemeriksaan Ibu Hamil Menggunakan User Experience Lifecycle Wardhana, Ariq Cahya; Fani, Tio; Adila, Nurul; Raharjo, Kukuh Pramadito
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 4, No 4 (2020): Oktober 2020
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v4i4.2294

Abstract

This research was aiming to produce an application design based on user experience. The research target to be achieved is the design of an online queue application for examining pregnant women using the User Experience Lifecycle (UXL). This study uses four stages of UXL, namely, analysis, design, prototype, and evaluation. The analysis produces application concepts consisting of flow models, work activity affinity diagrams, design requirements, and social models. The analysis phase is derived from questionnaire data distributed to 13 respondents. The design phase aims to design a persona, sketch, and storyboard. The prototype stage was developed based on the previous stage, producing a medium-fidelity prototype. Evaluations were carried out using the System Usability Scale (SUS) of 11 respondents producing a value of 76.46 or B (Good). Based on this, this research successfully used UXL for application design that has exceeded the minimum standard. Therefore, it is expected that the application design based on user experience will reduce the application developers' suggestions in designing the interface before moving to the production stage of the application.